© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18937
    Prev
    Next
    INDEX
    Explanations

    number ranges and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ijIJ
    -0.09
    æĪijä¹Łåİ»
    -0.08
    åħ§å¤ĸ
    -0.08
    ostro
    -0.08
    ļĮ
    -0.08
    大éĺµ
    -0.07
    æĸ°æĺŁ
    -0.07
    ä¸įè¨Ģ
    -0.07
    ÑĢеÑģ
    -0.07
    orry
    -0.07
    POSITIVE LOGITS
     depending
    0.14
    depending
    0.14
    Depending
    0.11
     Depending
    0.11
     whichever
    0.10
     tùy
    0.09
     dependendo
    0.09
     dependiendo
    0.09
    åıĸåĨ³äºİ
    0.08
    ä¸įçŃī
    0.08
    Activations Density 0.473%

    No Known Activations